Frequently asked questions
Who runs this site?
VoxMedica is an independent storefront for a cloud text-to-speech API. We help healthcare startups simplify integration by offering a straightforward API that mimics the familiar OpenAI endpoint structure. Our service is designed for developers who need reliable, clear audio outputs for patient education materials without the complexity of enterprise-grade contracts.
Are you affiliated with OpenAI?
No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We simply use the same request shape as the OpenAI speech endpoint, so their official SDKs work by changing the base URL to our API domain.
Are you affiliated with Azure?
No. We are not affiliated with Microsoft or Azure. We are an independent storefront providing a cloud text-to-speech API. Our service is designed for developers who need reliable, clear audio outputs for patient education materials without the complexity of enterprise-grade contracts.
Where are voices from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0). These sources include readings from LibriVox public-domain audiobooks. Every generated file carries an inaudible watermark that marks it as synthetic speech.
Is the license commercial?
Yes. The underlying voice recordings are from LibriTTS-R, licensed under CC BY 4.0.
Do you sell data?
No. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata, such as time, characters, and status, solely for billing purposes.
How do I contact you?
Support is by email only. We do not offer a phone number or live chat. You can reach us via the contact page on this site. Our team is available to assist with integration questions or billing inquiries through this dedicated email channel.
Is there a phone number?
No. We do not have a phone number. Support is provided exclusively via email. This allows us to maintain a straightforward, low-overhead service model for healthcare startups, focusing on reliable API performance rather than traditional enterprise support channels.
Do you have a physical office?
We are an independent storefront for a cloud API. We do not list a physical office location. Our service is entirely cloud-based, allowing developers to integrate our text-to-speech capabilities directly into their applications without needing to coordinate with a specific physical address.
When was the site created?
We focus on providing accurate, up-to-date information about our API capabilities, pricing, and voice options rather than tracking historical site launch dates for our independent storefront.
Do you have an SLA?
No. We do not offer a Service Level Agreement (SLA) or an uptime guarantee. Our service is designed for flexibility without enterprise-grade contracts. While we process requests efficiently, we do not guarantee specific availability percentages or compensation for downtime.
Are you HIPAA certified?
No. We do not have certifications like SOC 2 or HIPAA. We are an independent storefront for a cloud API. We do not offer on-premise installations or enterprise contracts that typically include such compliance certifications.
Do you have a BAA?
No. We do not offer a Business Associate Agreement (BAA). Our service is designed for straightforward API integration without the complexity of additional legal agreements.
How do I verify facts?
You can verify our facts by using our API endpoints directly. Call GET /v1/voices to see available voices and languages, or GET /v1/models to check model details. You can also test the POST endpoint with a small text input to confirm the audio output and format.
Who We Are
VoxMedica is an independent storefront for a cloud text-to-speech API. We simplify integration by mimicking the familiar OpenAI endpoint structure, allowing healthcare startups to generate audio files with minimal code changes. Our service is designed for developers who need reliable, clear audio outputs for patient education materials without the complexity of enterprise-grade contracts.
Independent storefront
We operate as a distinct entity, separate from major cloud providers.
Focus on simplicity
Our API uses standard HTTP requests. Send text, receive audio. We handle the synthesis engine, so you can focus on your application. The endpoint structure mirrors OpenAI’s speech endpoint, meaning you can use official OpenAI SDKs by simply changing the base URL. This reduces the learning curve for your development team.
Startup-friendly
We built this service for healthcare startups. There are no monthly plans, no seats, and no minimum spend. You pay only for what you use, starting with a free trial credit. This model aligns with the variable usage patterns common in early-stage product development and patient guide creation.
Voice Licensing
Our voices originate from the LibriTTS-R dataset, a curated collection of audiobook readings sourced from LibriVox.
LibriTTS-R source
We utilize the LibriTTS-R dataset as our core audio source.
CC BY 4.0 license
The underlying voice data is licensed under Creative Commons Attribution 4.0.
Public domain readings
The recordings are derived from public domain audiobook readings.
Data Policy
We prioritize your data privacy by ensuring that the input text you send for synthesis is used solely to generate the audio file. We do not use your input text for training.
Text not trained
The raw text you submit is processed only for the immediate generation of the audio response.
Audio not stored
Generated audio files are returned directly in the API response and are not retained on our servers after delivery.
Metadata for billing
We retain request metadata—such as timestamp, character count, and status—strictly to verify usage and process your billing accurately. This minimal data ensures you are charged correctly for the characters processed without retaining the content of your medical texts.
Technical Limits
We offer a straightforward API without the overhead of enterprise-grade contracts. Our service is designed for developers who need reliable, clear audio outputs for patient education materials without complex guarantees.
Understanding our technical boundaries helps you plan your integration accurately. We prioritize simplicity and transparency over marketing hype.
No SLA guarantee
We do not provide a Service Level Agreement or uptime guarantee. While we strive for stability, we do not promise specific availability percentages or compensation for outages.
No uptime promise
Our infrastructure is managed independently.
Queue processing
Requests are processed sequentially. Under heavy load, your synthesis request may wait in a queue before generation begins, potentially increasing latency for long texts.

Contact Information
We prioritize clear, asynchronous communication to keep our support team focused on resolving your technical questions efficiently. When you need assistance with API integration, billing, or voice selection, our email channel is the primary way we connect with developers.
Our streamlined process ensures that every inquiry receives a thoughtful, detailed response without the noise of real-time interruptions.
Email support only
All support requests are handled via email. This allows our team to thoroughly investigate issues and provide precise, documented solutions for your integration needs. You can reach us at the contact address provided on the /contact/ page.
No phone number
We do not offer a phone line for support. This decision reduces overhead and keeps our pricing competitive for startups. Most technical issues are resolved more efficiently through written documentation and code examples than through verbal explanation.
No live chat
There is no live chat widget on our site. This avoids the pressure of immediate responses and allows you to formulate your question clearly. You can take your time to describe the exact error or behavior you are experiencing.
Not Affiliated
VoxMedica is an independent storefront for the same text-to-speech API used by many, but we are not owned by any major tech company.
Not OpenAI official
We mimic the OpenAI endpoint structure for ease of use, but we are not affiliated with OpenAI.
Not Azure official
You interact directly with our API, not through an Azure portal or subscription.
Independent service
We are a standalone service designed for healthcare startups. Our billing, support, and technical limits are managed entirely by us, without dependency on the policies or outages of larger parent companies.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This consistency helps you predict costs for large volumes of patient guides or appointment reminders without tracking tiered usage.
23 languages
Any voice speaks any of these languages.
